Our new X account is live! Follow @wizwand_team for updates

Constrained Machine Translation on Sand-Glass Zh-En (test)

0.748Cometkiwi

deepseek-v3

Updated 4d ago

Evaluation Results

Method	Links
deepseek-v3 2026.01		0.748	-	0.941	0.287	46.3
gpt-5* 2026.01		0.746	-	0.947	0.3	-
claude-4.1-opus 2026.01		0.741	-	0.943	0.313	17.1
gemini-2.5-pro* 2026.01		0.739	-	0.941	0.307	-
gpt-5* 2026.01		0.705	-	0.928	0.345	-
deepseek-v3 2026.01		0.703	-	0.934	0.322	88.1
HOMURA (Reason) 2026.01		0.701	-	0.925	0.376	10.1
deepseek-v3 2026.01		0.7	-	0.924	0.307	12.4
HOMURA (Rubric) 2026.01		0.7	-	0.914	0.378	9.2
gemini-2.5-pro* 2026.01		0.698	-	0.927	0.322	-
claude-4.1-opus 2026.01		0.694	-	0.904	0.327	30.2
claude-4.1-opus 2026.01		0.691	-	0.907	0.376	12.2
claude-4.1-opus 2026.01		0.691	-	0.903	0.367	109.7
deepseek-v3 2026.01		0.691	-	0.902	0.332	122.6
gemini-2.5-pro* 2026.01		0.691	-	0.902	0.348	-
gpt-5* 2026.01		0.69	-	0.917	0.321	-
gemini-2.5-pro* 2026.01		0.673	-	0.904	0.276	-
gpt-5* 2026.01		0.673	-	0.906	0.296	-